Real-time identification of noise type contaminated in surface electromyogram signals using efficient statistical features.

Different types of noise contaminating the surface electromyogram (EMG) signal may degrade the recognition performance. For noise removal, the type of noise has to first be identified. In this paper, we propose a real-time efficient system for identifying a clean EMG signal and noisy EMG signals contaminated with any one of the following three types of noise: electrocardiogram interference, spike noise, and power line interference. Two statistical descriptors, kurtosis and skewness, are used as input features for the cascading quadratic discriminant analysis classifier. An efficient simplification of kurtosis and skewness calculations that can reduce computation time and memory storage is proposed. The experimental results from the real-time system based on an ATmega 2560 microcontroller demonstrate that the kurtosis and skewness values show root mean square errors between the traditional and proposed efficient techniques of 0.08 and 0.09, respectively. The identification accuracy with five-fold cross-validation resulting from the quadratic discriminant analysis classifier is 96.00%.

Reduced viral burden in paralytic compared to furious canine rabies is associated with prominent inflammation at the brainstem level.

BACKGROUND: The mechanisms that differentiate rabies infections into furious and paralytic forms remain undetermined. There are no neuropathological features in human brains that distinguish furious and paralytic rabies. This could be due to methodology and/or examination of specimens late in the disease course.In this study, postmortem examination of brain (5 furious and 5 paralytic) and spinal cord (3 furious and 3 paralytic) specimens was performed in 10 rabies-infected dogs, sacrificed shortly after developing the illness. Rabies virus (RABV) antigen (percentage of positive neurons, average antigen area in positive neurons and average antigen area per neuron) and RNA were quantified at 15 different central nervous system (CNS) regions. The distribution and degree of inflammation were also studied. RESULTS: More RABV antigen was detected in furious rabies than paralytic in many of the CNS regions studied. Caudal-rostral polarity of viral antigen distribution was found in both clinical forms in order from greatest to least: spinal cord, brainstem, cerebellum, midline structures (caudate, thalamus), hippocampus, and cerebrum. In contrast, RABV RNA was most abundant in the cerebral midline structures. Viral RNA was found at significantly higher levels in the cerebral cortex, thalamus, midbrain and medulla of dogs with the furious subtype. The RNA levels in the spinal cord were comparable in both clinical forms. A striking inflammatory response was found in paralytic rabies in the brainstem. CONCLUSIONS: These observations provide preliminary evidence that RABV antigen and RNA levels are higher in the cerebrum in furious rabies compared to the paralytic form. In addition, brainstem inflammation, more pronounced in paralytic rabies, may impede viral propagation towards the cerebral hemispheres.

Two-stage classification of electromyogram signals from hand grasps in the transverse plane.

This paper presents a two-stage classification to resolve the effect of arm position changes on electromyogram (EMG) classification for hand grasps in the transverse plane. The proposed method combines the EMG signals with the signals from an inertial measurement unit in both the position and motion classification stages. To improve accuracy, we incorporate EMG data from the upper arm and shoulder with the forearm EMG signals. When evaluated on the five alternative object grasps placed on the nine positions, the proposed technique yields an average total classification error of 0.9%, which is a substantial improvement over the single-stage classification (4.3%).

Contactless monitoring of human behaviors in bed using RSSI signals.

In this paper, contactless monitoring and classification of human activities and sleeping postures in bed using radio signals is presented. The major contribution of this work is the development of a contactless monitoring and classification system with a proposed framework that uses received signal strength indicator (RSSI) signals collected from only one wireless link, where different human activities and sleep postures, including (a) no one in the bed, (b) a man sitting on the bed, (c) sleeping on his back, (d) seizure sleeping, and (e) sleeping on his side, are tested. With our proposed system, there is no need to attach any sensors or medical devices to the human body or the bed. That is the limitation of the sensor-based technology. Additionally, our system does not raise a privacy concern, which is the major limitation of vision-based technology. Experiments using low-cost, low-power 2.4 GHz IEEE802.15.4 wireless networks have been conducted in laboratories. Results demonstrate that the proposed system can automatically monitor and classify human sleeping postures in real time. The average classification accuracy of activities and sleep postures obtained from different subjects, test environments, and hardware platforms is 99.92%, 98.87%, 98.01%, 87.57%, and 95.87% for cases (a) to (e), respectively. Here, the proposed system provides an average accuracy of 96.05%. Furthermore, the system can also monitor and separate the difference between the cases of the man falling from his bed and the man getting out of his bed. This autonomous system and sleep posture information can thus be used to support care people, physicians, and medical staffs in the evaluation and planning of treatment for the benefit of patients and related people. The proposed system for non-invasive monitoring and classification of human activities and sleeping postures in bed using RSSI signals.

Evaluation of feature projection techniques in object grasp classification using electromyogram signals from different limb positions.

A myoelectric prosthesis is manipulated using electromyogram (EMG) signals from the existing muscles for performing the activities of daily living. A feature vector that is formed by concatenating data from many EMG channels may result in a high dimensional space, which may cause prolonged computation time, redundancy, and irrelevant information. We evaluated feature projection techniques, namely principal component analysis (PCA), linear discriminant analysis (LDA), t-Distributed Stochastic Neighbor Embedding (t-SNE), and spectral regression extreme learning machine (SRELM), applied to object grasp classification. These represent feature projections that are combinations of either linear or nonlinear, and supervised or unsupervised types. All pairs of the four types of feature projection with seven types of classifiers were evaluated, with data from six EMG channels and an IMU sensors for nine upper limb positions in the transverse plane. The results showed that SRELM outperformed LDA with supervised feature projections, and t-SNE was superior to PCA with unsupervised feature projections. The classification errors from SRELM and t-SNE paired with the seven classifiers were from 1.50% to 2.65% and from 1.27% to 17.15%, respectively. A one-way ANOVA test revealed no statistically significant difference by classifier type when using the SRELM projection, which is a nonlinear supervised feature projection (p = 0.334). On the other hand, we have to carefully select an appropriate classifier for use with t-SNE, which is a nonlinear unsupervised feature projection. We achieved the lowest classification error 1.27% using t-SNE paired with a k-nearest neighbors classifier. For SRELM, the lowest 1.50% classification error was obtained when paired with a neural network classifier.

Multimodal Data Fusion of Electromyography and Acoustic Signals for Thai Syllable Recognition.

Speech disorders such as dysarthria are common and frequent after suffering a stroke. Speech rehabilitation performed by a speech-language pathologist is needed to improve and recover. However, in Thailand, there is a shortage of speech-language pathologists. In this paper, we present a syllable recognition system, which can be deployable in a speech rehabilitation system to provide support to the limited speech-language pathologists available. The proposed system is based on a multimodal fusion of acoustic signal and surface electromyography (sEMG) collected from facial muscles. Multimodal data fusion is studied to improve signal collection under noisy situations while reducing the number of electrodes needed. The signals are simultaneously collected while articulating 12 Thai syllables designed for rehabilitation exercises. Several features are extracted from sEMG signals and five channels are studied. The best combination of features and channels is chosen to be fused with the mel-frequency cepstral coefficients extracted from the acoustic signal. The feature vector from each signal source is projected by spectral regression extreme learning machine and concatenated. Data from seven healthy subjects were collected for evaluation purposes. Results show that the multimodal fusion outperforms the use of a single signal source achieving up to [Formula: see text] of accuracy. In other words, an accuracy improvement up to [Formula: see text] can be achieved when using the proposed multimodal fusion. Moreover, its low standard deviations in classification accuracy compared to those from the unimodal fusion indicate the improvement in the robustness of the syllable recognition.

Comparison of feature evaluation criteria for speech recognition based on electromyography.

In this paper, we present a performance comparison of 14 feature evaluation criteria and 4 classifiers for isolated Thai word classification based on electromyography signals (EMG) to find a near-optimal criterion and classifier. Ten subjects spoke 11 Thai number words in both audible and silent modes while the EMG signal from five positions of the facial and neck muscles were captured. After signal collection and preprocessing, 22 EMG features widely used in the EMG recognition field were computed and were then evaluated based on 14 evaluation criteria including both independent criteria (IC) and dependent criteria (DC) for feature evaluation and selection. Subsequently, the top nine features were selected for each criterion, and were used as inputs to classifiers. Four types of classifier were employed with 10-fold cross-validation to estimate classification performance. The results showed that features selected with a DC on a Fisher's least square linear discriminant classifier (D_FLDA) used with a linear Bayes normal classifier (LBN) gave the best average accuracies, of 93.25 and 80.12% in the audible and the silent modes, respectively.

Evaluation of feature extraction techniques and classifiers for finger movement recognition using surface electromyography signal.

Electromyography (EMG) in a bio-driven system is used as a control signal, for driving a hand prosthesis or other wearable assistive devices. Processing to get informative drive signals involves three main modules: preprocessing, dimensionality reduction, and classification. This paper proposes a system for classifying a six-channel EMG signal from 14 finger movements. A feature vector of 66 elements was determined from the six-channel EMG signal for each finger movement. Subsequently, various feature extraction techniques and classifiers were tested and evaluated. We compared the performance of six feature extraction techniques, namely principal component analysis (PCA), linear discriminant analysis (LDA), uncorrelated linear discriminant analysis (ULDA), orthogonal fuzzy neighborhood discriminant analysis (OFNDA), spectral regression linear discriminant analysis (SRLDA), and spectral regression extreme learning machine (SRELM). In addition, we also evaluated the performance of seven classifiers consisting of support vector machine (SVM), linear classifier (LC), naive Bayes (NB), k-nearest neighbors (KNN), radial basis function extreme learning machine (RBF-ELM), adaptive wavelet extreme learning machine (AW-ELM), and neural network (NN). The results showed that the combination of SRELM as the feature extraction technique and NN as the classifier yielded the best classification accuracy of 99%, which was significantly higher than those from the other combinations tested. Graphical abstract Mean of classification accuracies for 14 finger movements obtained with various pairs of SRELM and classifier.

Intracellular Spread of Rabies Virus Is Reduced in the Paralytic Form of Canine Rabies Compared to the Furious Form.

Studies of the furious and paralytic forms of canine rabies at the early stage of disease have shown a more rapid viral colonization of the cerebral hemispheres in the furious form, as measured by viral antigen within neuronal cell bodies and viral RNA levels. Measurement of cellular processes separate from neuronal cell body provides a visual record of the spread of rabies virus which occurs across synapses. In this study, the amount of rabies viral antigen within cell processes was quantitatively assessed by image analysis in a cohort of naturally rabies infected non-vaccinated dogs (5 furious and 5 paralytic) that were sacrificed shortly after developing illness. Measurements were taken at different levels of the spinal cord, brain stem, and cerebrum. Results were compared to the amount of rabies viral antigen in neuronal cell bodies. Generally, the amount of rabies viral antigen in cell processes decreased in a rostral direction, following the pattern for the amount of rabies viral antigen in neuronal cell bodies and the percentage of involved cell bodies. However, there was a delay in cell process involvement following cell body involvement, consistent with replication occurring in the cell body region and subsequent transport out to cell processes. Greater amounts of antigen were seen in cell processes in dogs with the furious compared to paralytic form, at all anatomic levels examined. This difference was even evident when comparing (1) neurons with similar amounts of antigen, (2) similar percentages of involved neurons, and (3) anatomic levels that showed 100% positive neurons. These findings suggest that intracellular transport of the virus may be slower in the paralytic form, resulting in slower viral propagation. Possible mechanisms might involve host-specific differences in intracellular virus transport. The latter could be cytokine-mediated, since previous studies have documented greater inflammation in the paralytic form.

Cell type classifiers for breast cancer microscopic images based on fractal dimension texture analysis of image color layers.

Having a classifier of cell types in a breast cancer microscopic image (BCMI), obtained with immunohistochemical staining, is required as part of a computer-aided system that counts the cancer cells in such BCMI. Such quantitation by cell counting is very useful in supporting decisions and planning of the medical treatment of breast cancer. This study proposes and evaluates features based on texture analysis by fractal dimension (FD), for the classification of histological structures in a BCMI into either cancer cells or non-cancer cells. The cancer cells include positive cells (PC) and negative cells (NC), while the normal cells comprise stromal cells (SC) and lymphocyte cells (LC). The FD feature values were calculated with the box-counting method from binarized images, obtained by automatic thresholding with Otsu's method of the grayscale images for various color channels. A total of 12 color channels from four color spaces (RGB, CIE-L*a*b*, HSV, and YCbCr) were investigated, and the FD feature values from them were used with decision tree classifiers. The BCMI data consisted of 1,400, 1,200, and 800 images with pixel resolutions 128 × 128, 192 × 192, and 256 × 256, respectively. The best cross-validated classification accuracy was 93.87%, for distinguishing between cancer and non-cancer cells, obtained using the Cr color channel with window size 256. The results indicate that the proposed algorithm, based on fractal dimension features extracted from a color channel, performs well in the automatic classification of the histology in a BCMI. This might support accurate automatic cell counting in a computer-assisted system for breast cancer diagnosis.

Post-beamforming second-order Volterra filter for pulse-echo ultrasonic imaging.

We present a new algorithm for deriving a second-order Volterra filter (SVF) capable of separating linear and quadratic components from echo signals. Images based on the quadratic components are shown to provide contrast enhancement between tissue and ultrasound contrast agents (UCAs) without loss in spatial resolution. It is also shown that the quadratic images preserve the low scattering regions due to their high dynamic range when compared with standard B-mode or harmonic images. A robust algorithm for deriving the filter has been developed and tested on real-time imaging data from contrast and tissue-mimicking media. Illustrative examples from image targets containing contrast agent and tissue-mimicking media are presented and discussed. Quantitative assessment of the contrast enhancement is performed on both the RF data and the envelope-detected log-compressed image data. It is shown that the quadratic images offer levels of enhancement comparable or exceeding those from harmonic filters while maintaining the visibility of low scattering regions of the image.

Quadratic B-mode (QB-Mode) Ultrasonic Imaging with Coded Transmit Waveforms.

In this paper, the use of coded transmit waveforms with post-beamforming nonlinear filtering of echo data in diagnostic ultrasound is presented. The nonlinear filter based on the second-order Volterra filter (SoVF) model separates the linear and quadratic echo components. The grayscale representation of the latter results in a new mode of imaging we refer to as quadratic B-mode (QB-mode). The use of chirp transmit waveforms in imaging contrast agents allows for nonlinear excitation of microbubble contrast agents (UCA) at a range of frequencies throughout the bandwidth of the transducer. The QB-mode image is shown to produce significant increase in UCA contrast over standard B-mode images from conventional and chirp excitation with and without compression. This contrast enhancement is achieved without loss in spatial resolution.